The Application of SIFT Method towards Image Registration

Shu Guang Wu; Shu He; Xia Yang

doi:10.4028/www.scientific.net/AMR.1044-1045.1392

Paper Titles

Technical Principle and Application of H3C IRF
p.1375

The Analysis and Design of the Dynamic Information Service System Network Architecture of the SOA Based on WAVE Technology
p.1380

The Application of Intelligence Distribution Network Communication Based on EPON
p.1384

The Application of Kernel Methods for Image Classification
p.1388

The Application of SIFT Method towards Image Registration
p.1392

The Design of the Enterprise Network Security Solutions
p.1397

The Development of Employee Information Management System
p.1401

The Oil and Gas Pipeline SCADA System Based on Cloud Computing and the Scheduling Algorithm
p.1406

The Present Botnet Protection Situation of the Data Center
p.1411

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 1044-1045The Application of SIFT Method towards Image...

The Application of SIFT Method towards Image Registration

Abstract:

The scale invariant features transform (SIFT) is commonly used in object recognition,According to the problems of large memory consumption and low computation speed in SIFT (Scale Invariant Feature Transform) algorithm.During the image registration methods based on point features,SIFT point feature is invariant to image scale and rotation, and provides robust matching across a substantial range of affine distortion. Experiments show that on the premise that registration accuracy is stable, the proposed algorithm solves the problem of high requirement of memory and the efficiency is improved greatly, which is applicable for registering remote sensing images of large areas.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 1044-1045)

Pages:

1392-1396

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1044-1045.1392

Citation:

Cite this paper

Online since:

October 2014

Authors:

Shu Guang Wu*, Shu He, Xia Yang

Keywords:

Image Registration, Point Feature, Scale Invariant Feature, SIFT Descriptor

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] David G. Lowe. Local Feature View Clustering for 3D Object Recognition[C]. Proc. of IEEE Conference on Computer Vision and Patten Recognition, Kauai, Hawaii, December (2001).

DOI: 10.1109/cvpr.2001.990541

Google Scholar

[2] Li Q L, Wang G Y, Liu J G and Chen S B. 2009. Robust scale-invariant feature matching for remote sensing image registration. IEEE Geoscience and Remote Sensing Letters, 6(2): 287–29.

DOI: 10.1109/lgrs.2008.2011751

Google Scholar

[3] David G. Lowe. Distinctive Image Features from Scale-Invariant Keypoints [J]. The International Journal of Computer Vision, (2004).

DOI: 10.1023/b:visi.0000029664.99615.94

Google Scholar

[4] Li F F, Xiao B L, Jia Y H and Mao X L. 2009. Improved SIFT algorithm and its application in automatic registration of remotelysensed imagery. Geomatics and Information Science of Wuhan University, 34(10): 1245–1249.

Google Scholar

[4] Dong L X. 2008. Estimation of the Forest Canopy Height and Above ground Biomass Based on Multiplicatel Remote Sensing in Three Gorges. Beijing: Institute of Remote Sensing Applications Chinese Academy of Sciences (CAS): 56–98.

Google Scholar

[5] A. Smola．Support Vector learning: Concepts and Algorithms．Tutorial given at ISCAS, [R] Sydney, 2001.

Google Scholar

[6] B. Scholkopf and A.J. Smola．Support Vector Machines and Kernel Algorithms[R]．In Encyclopedia of Biostatistics, John Wiley and Sons, (2003).

Google Scholar